Hi,
This is how I want my pipelines to work:-
Pipeline 4:
Has to get the source mac address and save it in 160th(160-167) meta data
filed in the mbuf.
Pipeline 5:
Will take the vlan id and store it in 168th(168-175) offset of the same mbuf
Pipeline 6:
Take the incoming port id which is in 23rd position of the mbuf and store
it in 175th offset. (It will overlap with vlan id field stored, but since I
need only that one bit and I have to access all the three fileds together
as a 16 bit key value, I have done this overlapping)
Pipeline 7:
Key offset is given as 160 and key size is given as 16. So that 160 to 175
will be available as we have stored those in meta data in the previous
three pipelines.
I want to know whether my logic will work if I write the config file as
shown below. Will pipeline 7 be able to get the stored source mac address,
vlan id and port id from the given key offset?
[PIPELINE4]
..
..
dma_size = 8
dma_dst_offset = 160
dma_src_offset = 262
dma_src_mask = FFFFFFFFFFFF0000
dma_hash_offset = 192
[PIPELINE5]
..
..
dma_size = 8
dma_dst_offset = 168
dma_src_offset = 268
dma_src_mask = 00000FFF00000000
dma_hash_offset = 200
[PIPELINE6]
..
..
dma_size = 8
dma_dst_offset = 175
dma_src_offset = 23
dma_src_mask = FF00000000000000
dma_hash_offset = 208
[PIPELINE7]
..
..
key_size = 16
key_offset = 160
key_mask = FFFFFFFFFFFF000000000FFF000000FF
..
Thanks for your reply and help.
Regards,
Nidhia Varghese
Hi,
Any comments on the below thread?
Thanks,
Nidhia
On Tue, May 30, 2017 at 12:33 PM, Nidhia Varghese <
nidhiavarghese93@gmail.com> wrote:
Hi,
This is how I want my pipelines to work:-
Pipeline 4:
Has to get the source mac address and save it in 160th(160-167) meta data
filed in the mbuf.
Pipeline 5:
Will take the vlan id and store it in 168th(168-175) offset of the same
mbuf
Pipeline 6:
Take the incoming port id which is in 23rd position of the mbuf and store
it in 175th offset. (It will overlap with vlan id field stored, but since I
need only that one bit and I have to access all the three fileds together
as a 16 bit key value, I have done this overlapping)
Pipeline 7:
Key offset is given as 160 and key size is given as 16. So that 160 to 175
will be available as we have stored those in meta data in the previous
three pipelines.
I want to know whether my logic will work if I write the config file as
shown below. Will pipeline 7 be able to get the stored source mac address,
vlan id and port id from the given key offset?
[PIPELINE4]
..
..
dma_size = 8
dma_dst_offset = 160
dma_src_offset = 262
dma_src_mask = FFFFFFFFFFFF0000
dma_hash_offset = 192
[PIPELINE5]
..
..
dma_size = 8
dma_dst_offset = 168
dma_src_offset = 268
dma_src_mask = 00000FFF00000000
dma_hash_offset = 200
[PIPELINE6]
..
..
dma_size = 8
dma_dst_offset = 175
dma_src_offset = 23
dma_src_mask = FF00000000000000
dma_hash_offset = 208
[PIPELINE7]
..
..
key_size = 16
key_offset = 160
key_mask = FFFFFFFFFFFF000000000FFF000000FF
..
Thanks for your reply and help.
Regards,
Nidhia Varghese
Hi Nidhia,
You should go ahead and test it. Did you test it and it did not work as you expect?
Personally, I cannot see any reasons why it should not work, but you need to test it yourself. I am assuming that pipelines 4, 5,6 below have the passthrough type and pipeline 7 has the flow classification type.
Regards,
Cristian
-----Original Message-----
From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Nidhia Varghese
Sent: Thursday, June 1, 2017 1:59 PM
To: users@dpdk.org; dev@dpdk.org
Subject: Re: [dpdk-dev] Getting meta data from different pipelines in
ip_pipeline application
Hi,
Any comments on the below thread?
Thanks,
Nidhia
On Tue, May 30, 2017 at 12:33 PM, Nidhia Varghese <
nidhiavarghese93@gmail.com> wrote:
quoted
Hi,
This is how I want my pipelines to work:-
Pipeline 4:
Has to get the source mac address and save it in 160th(160-167) meta data
filed in the mbuf.
Pipeline 5:
Will take the vlan id and store it in 168th(168-175) offset of the same
mbuf
Pipeline 6:
Take the incoming port id which is in 23rd position of the mbuf and store
it in 175th offset. (It will overlap with vlan id field stored, but since I
need only that one bit and I have to access all the three fileds together
as a 16 bit key value, I have done this overlapping)
Pipeline 7:
Key offset is given as 160 and key size is given as 16. So that 160 to 175
will be available as we have stored those in meta data in the previous
three pipelines.
I want to know whether my logic will work if I write the config file as
shown below. Will pipeline 7 be able to get the stored source mac address,
vlan id and port id from the given key offset?
[PIPELINE4]
..
..
dma_size = 8
dma_dst_offset = 160
dma_src_offset = 262
dma_src_mask = FFFFFFFFFFFF0000
dma_hash_offset = 192
[PIPELINE5]
..
..
dma_size = 8
dma_dst_offset = 168
dma_src_offset = 268
dma_src_mask = 00000FFF00000000
dma_hash_offset = 200
[PIPELINE6]
..
..
dma_size = 8
dma_dst_offset = 175
dma_src_offset = 23
dma_src_mask = FF00000000000000
dma_hash_offset = 208
[PIPELINE7]
..
..
key_size = 16
key_offset = 160
key_mask = FFFFFFFFFFFF000000000FFF000000FF
..
Thanks for your reply and help.
Regards,
Nidhia Varghese
Hi,
I tested it, but its not working as expected.
Pipelines 4,5 and 6 are passthrough pipelines and 7 is of flow
classification type. Packets are getting dropped at pipeline 7.
On Sat, Jun 3, 2017 at 6:01 PM, Dumitrescu, Cristian <
cristian.dumitrescu@intel.com> wrote:
Hi Nidhia,
You should go ahead and test it. Did you test it and it did not work as
you expect?
Personally, I cannot see any reasons why it should not work, but you need
to test it yourself. I am assuming that pipelines 4, 5,6 below have the
passthrough type and pipeline 7 has the flow classification type.
Regards,
Cristian
If you print the bytes of the key read by the flow classification pipeline, is it as expected? Make sure you don’t have bytes of random data (incorrect masks) or endianess issues.
From: Nidhia Varghese [mailto:nidhiavarghese93@gmail.com]
Sent: Sunday, June 4, 2017 8:20 AM
To: Dumitrescu, Cristian <redacted>
Cc: users@dpdk.org; dev@dpdk.org
Subject: Re: [dpdk-dev] Getting meta data from different pipelines in ip_pipeline application
Hi,
I tested it, but its not working as expected.
Pipelines 4,5 and 6 are passthrough pipelines and 7 is of flow classification type. Packets are getting dropped at pipeline 7.
On Sat, Jun 3, 2017 at 6:01 PM, Dumitrescu, Cristian <cristian.dumitrescu@intel.com<mailto:cristian.dumitrescu@intel.com>> wrote:
Hi Nidhia,
You should go ahead and test it. Did you test it and it did not work as you expect?
Personally, I cannot see any reasons why it should not work, but you need to test it yourself. I am assuming that pipelines 4, 5,6 below have the passthrough type and pipeline 7 has the flow classification type.
Regards,
Cristian
Regards,
Nidhia Varghese